Studien- und Masterarbeiten bei SCS

Wenn du Elektrotechnik, Informatik, Physik oder Mathematik studierst und zudem neugierig, lernfähig, kommunikativ und engagiert bist, dann hast du bei SCS die Möglichkeit, deine Studien-/ Masterarbeit zu realisieren. Die Arbeit wird im Normalfall zu zweit, in Ausnahmefällen von einer Person verfasst. Sie soll sowohl eine Forschungs- als auch eine Entwicklungskomponente enthalten.

Wenn du eine eigene Idee für deine Studien-/Masterarbeiten und die Unterstützung deines Professors hast, melde dich bei uns. Ansonsten lass dich von den nachfolgenden Ideen inspirieren. Wir helfen gerne bei der Umsetzung.

Mögliche Studien- und Masterarbeiten

  • Deep Learning with Curiosity and PerseveranceDeep Learning with Curiosity and Perseverance

    In January 2021, the Mars rover Curiosity reached the astonishing age of 3,000 Martian days (sols). While the new rover Perseverance landed on Mars a few months ago, Curiosity continues to capture images of the planet: several hundred thousand camera images are openly available on NASA’s website (https://mars.nasa.gov/msl/multimedia/raw-images/). Such a dataset is ideal for performing various deep-learning tasks that can bring significant value to the Mars exploration community.

  • Consensus at the Edge using Swarm IntelligenceConsensus at the Edge using Swarm Intelligence

    In distributed computer systems, it is usually imperative that the reliability of the overall system must be guaranteed despite unreliable processors and faulty networks. This especially requires the coordination of processes and the agreement of common data values for further computations.

    In the last decades, corresponding consensus protocols have been developed which allow, with more or less high security, the consistency of server states and data values in distributed systems relative to each other .Unfortunately, these protocols are unsuitable for applications where 1) the majority of processors may fail (down-nodes >> quorum), 2) only small memory footprints are allowed (consensus-at-the-edge), and 3) the determination of a master is not always possible (swarm approach).

    Accordingly, a swarm-intelligent consensus-at-the-edge software shall be developed that can keep data values consistent in an embedded system with up to 100 nodes.

  • Developing a Payed Web Service that Guarantees no Data CollectionDeveloping a Payed Web Service that Guarantees no Data Collection

    What happens with our data when you log-in to an online service, e. g. over a smartphone app? Is your complete usage profile forwarded to the company?

    Many online services, e. g. online newspapers, have a subscription model, where the user has to pay for its usage. It is valid to restrict access to paying customers, but is it necessary for a newspaper to know exactly what articles were read by which customers? The goal of this thesis is to evaluate an approach that obfuscates the actual usage of a service, while maintaining the possibility to restrict access to paying customers.

  • Privacy Preserving OAuth Service with TEEsPrivacy Preserving OAuth Service with TEEs

    If we use Google, Facebook, or SwissID logins for third party sites, these login providers get to know when we log into which service. Moreover, the user has only little control over which data from her/his Google or Facebook accounts are shared with the service she/he’s logging into.

    The goal of this thesis is to build a blind OAuth service, which can be easily integrated into third party sites just like the above mentioned services.

  • Automating DDH Diagnosis using Machine/Deep Learning TechniquesAutomating DDH Diagnosis using Machine/Deep Learning Techniques

    Between 2 and 3 percent of all infants are diagnosed with developmental dysplasia of the hip (DDH), and it is believed that approximately 30% of all hip replacement surgeries on patients below the age of 60 are owed to DDH. Graf’s Method – the state of the art for diagnosis of DDH in infants – can aid to initiate early on, non-invasive treatment of infants with very high success rates.

  • Jogging with Acoustic Feedback based on Body RhythmsJogging with Acoustic Feedback based on Body Rhythms

    Jogging has become very popular in recent years, with millions of people across the world integrating it into their regular exercise regime. Many, however, do so with poor movement coordination, particularly in terms of the synchronization of body rhythms such as cadence, breathing and heartbeats. In this Master’s thesis, we aim to develop a digital application that will support runners in finding their natural jogging ‘groove’ by providing them with acoustic, real-time feedback on their individual style and technique.

  • Generating 3D Indoor Maps Autonomously Through Reiforcement LearningGenerating 3D Indoor Maps Autonomously Through Reiforcement Learning

    In September 2017, Unity Technologies released the first open beta of the Unity Machine Learning Agents Toolkit. With this toolkit, it is possible to train agents (e.g. through reinforcement learning) to solve a specific task in a simulated environment.

  • Deep Learning in the WildDeep Learning in the Wild

    Climate change and human exploitation of our planet has a significant influence on the habitat and existence of wild animals. The resulting biodiversity loss threatens ecosystems and the human development that depends on them. Protecting these habitats is based on delivering evidence by collecting data. This is usually labour intensive, since it depends on field work done by biologist and volunteers.

    This master thesis tries to make a contribution to scale up this important process by using acoustic detection of animals using deep learning on embedded systems.

  • Building a new Ecological and Private CryptocurrencyBuilding a new Ecological and Private Cryptocurrency
    encointer proposes a new blockchain-based cryptocurrency with an ecological consensus mechanism using trusted execution environments and an egalitarian money supply policy, where money issuance is done by individuals attending randomized pseudonym key signing events. encointer also features scalable private transactions and trustless off-chain smart contracts. This thesis shall build an encointer testnet based on Hyperledger Sawtooth. Depending on the student’s preference, emphasis ...
  • Automatisierte Anamnese von Heizungen und GebäudeenergieanlagenAutomatisierte Anamnese von Heizungen und Gebäudeenergieanlagen
    In der Schweiz besteht ein grosses Energieeffizienzpotential in Gebäuden. Bestehende Heizungsanlagen in Gebäuden sind heute oft nicht ideal eingestellt, weisen Mängel auf oder sind gar dysfunktional. Zur Detektion dieser Mängel soll ein Prototyp eines automatisierten Anamnese-Systems aufgebaut werden, welches aufgrund von sensorischen Messgrössen (primär Temperaturfühler) die Anlage erstens identifiziert, zweitens auf Fehler analysiert und drittens ...
  • Software-Architecture for SDRSoftware-Architecture for SDR
    Alle aktuellen SDR Softwarepakete haben Einschränkungen. Es gibt GNU Radio, welches kompliziert und schwierig zu bedienen ist, und es gibt verschiedene SDR GUIs, welche jedoch nicht einfach erweiterbar sind. Das Ziel ist eine einfach zu bedienende Software zu erstellen, welche es ermöglicht, Radiosignale zu analysieren und Algorithmen auszuprobieren. Fertige Abläufe sollen dann auf Knopfdruck in eine C-Datei exportiert werden können, um eine Integration in Embedded Systeme so leicht wie möglich zu gestalten.

  • Virtual Reality as 3D Ground Truth Generator for AI, Machine Learning and Deep LearningVirtual Reality as 3D Ground Truth Generator for AI, Machine Learning and Deep Learning

    Training effective Artificial Intelligence (AI) algorithms today often requires large amounts of ground truth data. Typically, this is a laborious, costly and time-consuming process often requiring manual adjustment. These problems can be overcome by combining AI with Virtual Reality (VR): an emerging technology with various applications in medicine, training, business and simulation. VR creates artificial environments that often resemble our real world.This project aims at exploring the potential of VR as 3D ground truth generator for state-of-the-art Machine Learning (ML) and Deep Learning (DL) Algorithms.

  • Transfer Learning for Image Segmentation using Convolutional Neural NetworksTransfer Learning for Image Segmentation using Convolutional Neural Networks

    Today’s Machine Learning (ML) success is often limited by a lack of labelled ground truth (GT) data to train the models. This is especially true for applications in medical imaging.Transfer learning (TL) is a state-of-art ML-technique that can be useful to overcome this problem for similar yet distinct tasks. TL tries to apply knowledge or models gained from a task to a second one. In the field of image recognition, TL-methods for deep neural nets re-use parameters trained on source domain data except for the output layer (see image on the right).In medical optical coherence tomography (OCT) of the eye only a limited set of GT-labeled images exists. In addition, there are several device manufacturers and imaging approaches. Thus, transfer learning could 1) enable an easier addition of new device types or imaging techniques, 2) improve the quality of available segmentations even with limited data.

  • Towards User-independent 2D / 3D Object Classification of Complex Life Science ImagesTowards User-independent 2D / 3D Object Classification of Complex Life Science Images

    We develop novel machine vision & mathematical morphology algorithms to analyze complex multi-modal Life Science images.

  • AI-based Golf-Coach with Automated Swing AnalysisAI-based Golf-Coach with Automated Swing Analysis

    Der Golfschwung gilt als einer der komplexesten Bewegungsabläufe aller Sportarten. Für den Amateurgolfer besteht die Schwierigkeit darin, bei einem Fehlschlag den Fehler in seiner Bewegung zu erkennen und entsprechend zu korrigieren.

    Das Ziel dieser Arbeit ist die automatisierte Analyse des Bewegungsablaufs des Golfspielers anhand von Filmaufnahmen, gezieltes Erkennen fehlerhafter Muster, sowie das Ausgeben von Korrekturvorschlägen.

  • Decentralized Ledger eVoting SystemDecentralized Ledger eVoting System

    eVoting is an unsolved problem, mainly because of security concerns connected to centralized IT systems. Blockchain technology enables new ways to solve IT problems in a transparent, tamper-proof and decentralized way. However, scalability of such solutions is still unsatisfactory and there’s still no solution that provides privacy of the single voter and transparency of the overall voting process at the same time.This master thesis aims at implementing a voting solution that scales to Swiss national votes. The technologies to be used could include zero knowledge proofs (zk-SNARKS), homomorphic encryption and smart contracts on a public blockchain (i.e. ethereum). Different layer-two technologies shall be evaluated to provide scalability for this use case.